AI Threat Alert indexes 4,319+ peer-reviewed and preprint papers on AI/ML security — covering adversarial attacks, model defenses, red-teaming benchmarks, surveys, and security tooling. Papers are sourced from arXiv, classified by type and by relevance to real-world threats, and cross-referenced with the CVEs and incidents they relate to.
Showing 141–160 of 275 papers
Clear filtersChengquan Guo, Xiaodong Liu, Weiwei Yang +7 more
LLM agents are increasingly adopted in long-horizon tasks and interact with diverse external environments. Despite their growing capabilities, these...
Michał Burzyński, Noah T. Rossi, Shomit Basu +1 more
Automated jailbreak discovery aims to find prompts that elicit prohibited behaviors from safety-trained language models, helping developers identify...
Long Dang, Ali Alfatemi, Kaiqi Xiong +4 more
Distributed machine learning (DML), including conventional distributed training and federated learning (FL), enables collaborative model development...
Gerardo Iuliano, Gabriele De Vito, Dario Di Nucci
Smart contracts are immutable programs deployed on blockchain platforms, where vulnerabilities can translate directly into financial loss. Among the...
Yukai Zhou, Wenjie Wang
A binary success indicator is a natural representation for discriminative tasks such as image classification under adversarial perturbations, where...
Jonathan F. Jao, Andrew Kyle Lampinen
Automated red-team auditing of language models is an important way to evaluate safety-relevant behaviors. These audits implicitly search a tree of...
Pengfei Zeng, Changhua Luo, Penghui Li
Large language models (LLMs) have enabled more effective vulnerability scanning of web applications. However, these capabilities also make it...
Kshitish Ghate, Michael Saxon, Tadayoshi Kohno +1 more
Large language models (LLMs) are often conditioned into specific roles such as tutors, interviewers, or agents acting for an organisation, through...
Igor Shilov, Xiaoxue Yang, Alexander Panfilov +6 more
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head...
Yuelin Han
Prior work framed the envelope layer as the channel through which malicious content enters an agent, and established it as a defense surface...
Abhijit Mazumdar, Manuela L. Bujorianu, Rafal Wisniewski
In this letter, we investigate a notion of probabilistic safety for a stochastic dynamical system. Standard safety notions are based on the idea that...
Hongyan Chang, Hady Elsahar, Tom Sander +10 more
Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trains a student model on the...
Vincess Dongmo, Astride Melvin Fokam Ninyim
Multi-relational graph detectors learn from clean data how much to trust each relation, but an adversary pays a different price to manipulate each...
Krishna Kanth Nakka, Yujun Wang, Shijie Zhou +3 more
Reliable evaluation is a critical bottleneck in privacy red-teaming of large language models (LLMs): determining whether a jailbreak response...
Indraveni Chebolu, Seema Panghal, Arnab Mallick +1 more
Security pipelines often fuse several data sources and protect a downstream model with a cross-source anomaly detector. Such detectors are usually...
Yuchen Zhang, Yaxiong Wang, Yujiao Wu +6 more
Multimodal forgery detection is commonly studied under a static assumption: training attacks are expected to approximate those encountered after...
Zihan Chen, Lei Nico Zheng, Di Zhu
Attack logs and red-team reports show targets the attacks used against them, to help them repair their defenses. Prompt injections against large...
Saim Rehman, Muhammad Shafique
Compact electroencephalography (EEG) decoders enable embedded brain--computer interfaces (BCIs), but compression can alter adversarial robustness...
Tushar Nayan, Pratik Poudel, Qian Lou +3 more
Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access controls. These prompts are...
Junle Li, Siqi Chen, Jiakai Li +1 more
Multi-turn jailbreaks turn dialogue safety into a trace property: a violation may become identifiable only when user intent and assistant behavior...
AI security research studies how AI and machine-learning systems can be attacked and defended — covering adversarial examples, prompt injection, model poisoning, training-data extraction, and the mitigations against them. AI Threat Alert curates this research from academic sources so security teams can track the threats behind emerging AI risks.
AI Threat Alert indexes 4,319+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Papers are sourced from arXiv, then classified by type and by relevance to real-world AI/ML threats, and cross-referenced with the CVEs and incidents they relate to.
Coverage spans adversarial attacks, model and system defenses, red-teaming benchmarks, literature surveys, and security tooling for LLMs, ML libraries, AI agents, and inference pipelines.
Every paper is filtered for AI security relevance and linked to the vulnerabilities, vendors, and incidents it relates to, so the research connects directly to operational threat intelligence.
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert